[OpenMP] Change the nextgen plugin kernel thread count scheme as old plugins'

[jdoerfert]

LG, does this fix your issue (regardless, we want this for now)

openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp

AsyncInfoWrapperTy::~AsyncInfoWrapperTy() {
   // synchronize explicitly when the object is deleted.
   if (AsyncInfoPtr == &LocalAsyncInfo && LocalAsyncInfo.Queue && !Err)
     Err = Device.synchronize(&LocalAsyncInfo);
 }
 
 Error GenericKernelTy::init(GenericDeviceTy &GenericDevice,
                             DeviceImageTy &Image) {
   PreferredNumThreads = getDefaultNumThreads(GenericDevice);
-  if (isGenericMode())
-    PreferredNumThreads += GenericDevice.getWarpSize();
 
   MaxNumThreads = GenericDevice.getThreadLimit();
 
   DynamicMemorySize = GenericDevice.getDynamicMemorySize();
 
   return initImpl(GenericDevice, Image);
 }
 
for (int I = 0; I < NumArgs; ++I) {
     Ptrs[I] = (void *)((intptr_t)ArgPtrs[I] + ArgOffsets[I]);
     Args[I] = &Ptrs[I];
   }
   return &Args[0];
 }
 
 uint32_t GenericKernelTy::getNumThreads(GenericDeviceTy &GenericDevice,
                                         uint32_t ThreadLimitClause) const {
+  if (ThreadLimitClause > 0 && isGenericMode())
+    ThreadLimitClause += GenericDevice.getWarpSize();
+
   return std::min(MaxNumThreads, (ThreadLimitClause > 0) ? ThreadLimitClause
                                                          : PreferredNumThreads);
 }
 
 uint64_t GenericKernelTy::getNumBlocks(GenericDeviceTy &GenericDevice,
                                        uint64_t NumTeamsClause,
                                        uint64_t LoopTripCount,
                                        uint32_t NumThreads) const {